# PRO: Projection Domain Synthesis for CT Imaging

arXiv: https://arxiv.org/abs/2506.13443 · HTML: https://mlsanity.com/paper/2506.13443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Improved Techniques for Training Score-Based Generative Models](https://mlsanity.com/paper/2006.09011/) (2020)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Solving Inverse Problems in Medical Imaging with Score-Based Generative Models](https://mlsanity.com/paper/2111.08005/) (2021)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Invertible generative models for inverse problems: mitigating representation error and dataset bias](https://mlsanity.com/paper/1905.11672/) (2019)
- [MAISI: Medical AI for Synthetic Imaging](https://mlsanity.com/paper/2409.11169/) (2024)
- [A review: Deep learning for medical image segmentation using multi-modality fusion](https://mlsanity.com/paper/2004.10664/) (2020)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1908.02498/) (2019)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [MR image reconstruction using deep density priors](https://mlsanity.com/paper/1711.11386/) (2017)
- [Generative Modeling in Sinogram Domain for Sparse-view CT Reconstruction](https://mlsanity.com/paper/2211.13926/) (2022)
- [Stage-by-stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2308.15942/) (2023)
- [Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods](https://mlsanity.com/paper/2012.04580/) (2020)
- [Masked Sinogram Model with Transformer for ill-Posed Computed Tomography Reconstruction: a Preliminary Study](https://mlsanity.com/paper/2209.01356/) (2022)

## Built on by (most cited first, 1 of 1)

- [Prompt Mechanisms in Medical Imaging: A Comprehensive Survey](https://mlsanity.com/paper/2507.01055/) (2025)

## Abstract (arXiv)

Synthetic CT projection data is crucial for advancing imaging research, yet its generation remains challenging. Current image domain methods are limited as they cannot simulate the physical acquisition process or utilize the complete statistical information present in projection data, restricting their utility and fidelity. In this work, we present PRO, a projection domain synthesis foundation model for CT imaging. To the best of our knowledge, this is the first study that performs CT synthesis in the projection domain. Unlike previous approaches that operate in the image domain, PRO learns rich structural representations from projection data and leverages anatomical text prompts for controllable synthesis. Projection data generation models can utilize complete measurement signals and simulate the physical processes of scanning, including material attenuation characteristics, beam hardening, scattering, and projection geometry, and support research on downstream imaging tasks. Moreover, PRO functions as a foundation model, capable of generalizing across diverse downstream tasks by adjusting its generative behavior via prompt inputs. Experimental results demonstrated that incorporating our synthesized data significantly improves performance across multiple downstream tasks, including low-dose and sparse-view reconstruction. These findings underscore the versatility and scalability of PRO in data generation for various CT applications. These results highlight the potential of projection domain synthesis as a powerful tool for data augmentation and robust CT imaging. Our source code is publicly available at: https://github.com/yqx7150/PRO.